# ******************************************************************************
# *
-# * Copyright (C) 1995-2006, International Business Machines
+# * Copyright (C) 1995-2012, International Business Machines
# * Corporation and others. All Rights Reserved.
# *
# ******************************************************************************
# If this converter alias table looks very confusing, a much easier to
# understand view can be found at this demo:
-# http://www.ibm.com/software/globalization/icu/demo/converters
+# http://demo.icu-project.org/icu-bin/convexp
# IMPORTANT NOTE
#
# This is an alias file used by the character set converter.
# A lot of converter information can be found in unicode/ucnv.h, but here
# is more information about this file.
-#
+#
+# If you are adding a new converter to this list and want to include it in the
+# icu data library, please be sure to add an entry to the appropriate ucm*.mk file
+# (see ucmfiles.mk for more information).
+#
# Here is the file format using BNF-like syntax:
#
# converterTable ::= tags { converterLine* }
ibm-17593 { IBM } # Unicode 4.0, UTF-8
windows-65001 { WINDOWS* }
cp1208
+ x-UTF_8J
+ unicode-1-1-utf-8
+ unicode-2-0-utf-8
# The ICU 2.2 UTF-16/32 converters detect and write a BOM.
UTF-16 { IANA* MIME* JAVA* } ISO-10646-UCS-2 { IANA }
# and they are a subset of Unicode. ICU does not support their encoding structures.
# 1400 1401 1402 1410 1414 1415 1446 1447 1448 1449 64770 64771 65520 5496 5497 5498 9592 13688
UTF-16BE { IANA* MIME* JAVA* } x-utf-16be { JAVA }
+ UnicodeBigUnmarked { JAVA } # java.io name
ibm-1200 { IBM* } # UTF-16 BE with IBM PUA
ibm-1201 { IBM } # UTF-16 BE
ibm-13488 { IBM } # Unicode 2.0, UTF-16 BE with IBM PUA
ibm-21681 { IBM } # Unicode 4.0, UTF-16 BE
ibm-25776 { IBM } # Unicode 4.1, UTF-16 BE with IBM PUA
ibm-25777 { IBM } # Unicode 4.1, UTF-16 BE
+ ibm-29872 { IBM } # Unicode 5.0, UTF-16 BE with IBM PUA
+ ibm-29873 { IBM } # Unicode 5.0, UTF-16 BE
ibm-61955 { IBM } # UTF-16BE with Gaidai University (Japan) PUA
- ibm-61956 { IBM } # UTF-16BE with HKSCS-Big 5 PUA
+ ibm-61956 { IBM } # UTF-16BE with Microsoft HKSCS-Big 5 PUA
windows-1201 { WINDOWS* }
cp1200
cp1201
# ibm-61952 is not a valid CCSID because it's Unicode 1.1
# ibm-61953 is not a valid CCSID because it's Unicode 1.0
UTF-16LE { IANA* MIME* JAVA* } x-utf-16le { JAVA }
+ UnicodeLittleUnmarked { JAVA } # java.io name
ibm-1202 { IBM* } # UTF-16 LE with IBM PUA
ibm-1203 { IBM } # UTF-16 LE
ibm-13490 { IBM } # Unicode 2.0, UTF-16 LE with IBM PUA
ibm-21683 { IBM } # Unicode 4.0, UTF-16 LE
ibm-25778 { IBM } # Unicode 4.1, UTF-16 LE with IBM PUA
ibm-25779 { IBM } # Unicode 4.1, UTF-16 LE
+ ibm-29874 { IBM } # Unicode 5.0, UTF-16 LE with IBM PUA
+ ibm-29875 { IBM } # Unicode 5.0, UTF-16 LE
UTF16_LittleEndian
windows-1200 { WINDOWS* }
UTF-32BE { IANA* } UTF32_BigEndian
ibm-1232 { IBM* } # UTF-32 BE with IBM PUA
ibm-1233 { IBM } # UTF-32 BE
+ ibm-9424 { IBM } # Unicode 4.1, UTF-32 BE with IBM PUA
UTF-32LE { IANA* } UTF32_LittleEndian
ibm-1234 { IBM* } # UTF-32 LE, with IBM PUA
ibm-1235 { IBM } # UTF-32 LE
UTF32_PlatformEndian
UTF32_OppositeEndian
+
+# Java-specific, non-Unicode-standard UTF-16 variants.
+# These are in the Java "Basic Encoding Set (contained in lib/rt.jar)".
+# See the "Supported Encodings" at
+# http://java.sun.com/javase/6/docs/technotes/guides/intl/encoding.doc.html
+# or a newer version of this document.
+#
+# Aliases marked with { JAVA* } are canonical names for java.io and java.lang APIs.
+# Aliases marked with { JAVA } are canonical names for the java.nio API.
+#
+# "BOM" means the Unicode Byte Order Mark, which is the encoding-scheme-specific
+# byte sequence for U+FEFF.
+# "Reverse BOM" means the BOM for the sibling encoding scheme with the
+# opposite endianness. (LE<->BE)
+
+# "Sixteen-bit Unicode (or UCS) Transformation Format, big-endian byte order,
+# with byte-order mark"
+#
+# From Unicode: Writes BOM.
+# To Unicode: Detects and consumes BOM.
+# If there is a "reverse BOM", Java throws
+# MalformedInputException: Incorrect byte-order mark.
+# In this case, ICU4C sets a U_ILLEGAL_ESCAPE_SEQUENCE UErrorCode value
+# and a UCNV_ILLEGAL UConverterCallbackReason.
+UTF-16BE,version=1 UnicodeBig { JAVA* }
+
+# "Sixteen-bit Unicode (or UCS) Transformation Format, little-endian byte order,
+# with byte-order mark"
+#
+# From Unicode: Writes BOM.
+# To Unicode: Detects and consumes BOM.
+# If there is a "reverse BOM", Java throws
+# MalformedInputException: Incorrect byte-order mark.
+# In this case, ICU4C sets a U_ILLEGAL_ESCAPE_SEQUENCE UErrorCode value
+# and a UCNV_ILLEGAL UConverterCallbackReason.
+UTF-16LE,version=1 UnicodeLittle { JAVA* } x-UTF-16LE-BOM { JAVA }
+
+# This one is not mentioned on the "Supported Encodings" page
+# but is available in Java.
+# In Java, this is called "Unicode" but we cannot give it that alias
+# because the standard UTF-16 converter already has a "unicode" alias.
+#
+# From Unicode: Writes BOM.
+# To Unicode: Detects and consumes BOM.
+# If there is no BOM, rather than defaulting to BE, Java throws
+# MalformedInputException: Missing byte-order mark.
+# In this case, ICU4C sets a U_ILLEGAL_ESCAPE_SEQUENCE UErrorCode value
+# and a UCNV_ILLEGAL UConverterCallbackReason.
+UTF-16,version=1
+
+# This is the same as standard UTF-16 but always writes a big-endian byte stream,
+# regardless of the platform endianness, as expected by the Java compatibility tests.
+# See the java.nio.charset.Charset API documentation at
+# http://java.sun.com/javase/6/docs/api/java/nio/charset/Charset.html
+# or a newer version of this document.
+#
+# From Unicode: Write BE BOM and BE bytes
+# To Unicode: Detects and consumes BOM. Defaults to BE.
+UTF-16,version=2
+
+# Note: ICU does not currently support Java-specific, non-Unicode-standard UTF-32 variants.
+# Presumably, these behave analogously to the UTF-16 variants with similar names.
+# UTF_32BE_BOM x-UTF-32BE-BOM
+# UTF_32LE_BOM x-UTF-32LE-BOM
+
+# End of Java-specific, non-Unicode-standard UTF variants.
+
+
# On UTF-7:
# RFC 2152 (http://www.imc.org/rfc2152) allows to encode some US-ASCII
# characters directly or in base64. Especially, the characters in set O
#
# For details about email headers see RFC 2047.
UTF-7 { IANA* MIME* WINDOWS } windows-65000 { WINDOWS* }
+ unicode-1-1-utf-7
+ unicode-2-0-utf-7
# UTF-EBCDIC doesn't exist in ICU, but the aliases are here for reference.
#UTF-EBCDIC ibm-1210 { IBM* } ibm-1211 { IBM }
IMAP-mailbox-name
SCSU { IANA* }
- ibm-1212 { IBM* } # SCSU with IBM PUA
- ibm-1213 { IBM } # SCSU
+ ibm-1212 { IBM } # SCSU with IBM PUA
+ ibm-1213 { IBM* } # SCSU
BOCU-1 { IANA* }
csBOCU-1 { IANA }
- ibm-1214 { IBM* } # BOCU-1 with IBM PUA
- ibm-1215 { IBM } # BOCU-1
+ ibm-1214 { IBM } # BOCU-1 with IBM PUA
+ ibm-1215 { IBM* } # BOCU-1
# See http://www.unicode.org/unicode/reports/tr26 for this Compatibility Encoding Scheme for UTF-16
# The Unicode Consortium does not encourage the use of CESU-8
ascii7 { JAVA }
646 { JAVA }
windows-20127 { WINDOWS* }
- # IBM367 { IANA WINDOWS } # This isn't the default ibm-367.
+ ibm-367 { IBM* } IBM367 { IANA WINDOWS } # This is not truely ibm-367 because it's missing the fallbacks.
# GB 18030 is partly algorithmic, using the MBCS converter
-gb18030 { IANA* } ibm-1392 { IBM* } windows-54936 { WINDOWS* }
+gb18030 { IANA* } ibm-1392 { IBM* } windows-54936 { WINDOWS* } GB18030 { MIME* }
# Table-based interchange codepages
-ibm-367_P100-1995 { UTR22* } ibm-367 { IBM* } IBM367 { IANA* } # This is ASCII, but it has fallbacks
-
# Central Europe
ibm-912_P100-1995 { UTR22* }
ibm-912 { IBM* JAVA }
915 { JAVA }
windows-28595 { WINDOWS* }
+glibc-PT154-2.3.3 { UTR22* }
+ PTCP154 { IANA* }
+ csPTCP154
+ PT154
+ CP154
+ Cyrillic-Asian
+
# Arabic
# ISO_8859-6-E and ISO_8859-6-I are similar to this charset, but BiDi is done differently
# From a narrow mapping point of view, there is no difference.
windows-28596 { WINDOWS* }
ISO-8859-6-I { IANA MIME } # IANA considers this alias different and BiDi needs to be applied.
ISO-8859-6-E { IANA MIME } # IANA considers this alias different and BiDi needs to be applied.
+ x-ISO-8859-6S { JAVA }
# ISO Greek (with euro update). This is really ISO_8859-7:2003
-ibm-9005_X100-2005 { UTR22* }
+ibm-9005_X110-2007 { UTR22* }
ibm-9005 { IBM* }
ISO-8859-7 { MIME* IANA WINDOWS }
greek { IANA WINDOWS }
iso-ir-126 { IANA WINDOWS }
ISO_8859-7:1987 { IANA* WINDOWS }
windows-28597 { WINDOWS* }
+ sun_eu_greek # For Solaris
# ISO Greek (w/o euro update)
# JDK 1.5 has these aliases.
# From a narrow mapping point of view, there is no difference.
# -E means explicit. -I means implicit.
# -E requires the client to handle the ISO 6429 bidirectional controls
-ibm-916_P100-1995 { UTR22* }
- ibm-916 { IBM* JAVA }
+# This matches the official mapping on unicode.org
+ibm-5012_P100-1999 { UTR22* }
+ ibm-5012 { IBM* }
ISO-8859-8 { MIME* IANA WINDOWS JAVA* }
hebrew { IANA WINDOWS JAVA }
csISOLatinHebrew { IANA WINDOWS JAVA }
ISO-8859-8-I { IANA MIME } # IANA and Windows considers this alias different and BiDi needs to be applied.
ISO-8859-8-E { IANA MIME } # IANA and Windows considers this alias different and BiDi needs to be applied.
8859_8 { JAVA }
+ windows-28598 { WINDOWS* } # Hebrew (ISO-Visual). A hybrid between ibm-5012 and ibm-916 with extra PUA mappings.
+ hebrew8 # Reflect HP-UX code page update
+
+# Unfortunately, the Java aliases are split across ibm-916 and ibm-5012
+# Also many platforms are a combination between ibm-916 and ibm-5012 behaviors
+ibm-916_P100-1995 { UTR22* }
+ ibm-916 { IBM* JAVA* }
cp916 { JAVA }
916 { JAVA }
- windows-28598 { WINDOWS* }
# Turkish
ibm-920_P100-1995 { UTR22* }
920 { JAVA }
windows-28599 { WINDOWS* }
ECMA-128 # IANA doesn't have this alias 6/24/2002
+ turkish8 # Reflect HP-UX codepage update 8/1/2008
+ turkish # Reflect HP-UX codepage update 8/1/2008
# Nordic languages
iso-8859_10-1998 { UTR22* } ISO-8859-10 { MIME* IANA* }
# ISO-8859-11 is a superset of TIS-620. The difference is that ISO-8859-11 contains the C1 control codes.
iso-8859_11-2001 { UTR22* } ISO-8859-11
thai8 # HP-UX alias. HP-UX says TIS-620, but it's closer to ISO-8859-11.
+ x-iso-8859-11 { JAVA* }
# iso-8859-13, PC Baltic (w/o euro update)
ibm-921_P100-1995 { UTR22* }
ibm-921 { IBM* }
ISO-8859-13 { IANA* MIME* JAVA* }
8859_13 { JAVA }
+ windows-28603 { WINDOWS* }
cp921
921
+ x-IBM921 { JAVA }
# Celtic
iso-8859_14-1998 { UTR22* } ISO-8859-14 { IANA* }
sjis78
ibm-942_VSUB_VPUA
ibm-932_VSUB_VPUA
+ x-IBM942 { JAVA* }
+ x-IBM942C { JAVA }
# Is this "JIS_C6226-1978"?
# ibm-943_P15A-2003 differs from windows-932-2000 only in a few roundtrip mappings:
pck # Probably SOLARIS
sjis # This might be for ibm-1351
ibm-943_VSUB_VPUA
+ x-MS932_0213 { JAVA }
+ x-JISAutoDetect { JAVA }
# cp943 # This isn't Windows, and no one else uses it.
# IANA says that Windows-31J is an extension to csshiftjis ibm-932
ibm-943_P130-1999 { UTR22* }
cp943 { JAVA* } # This is slightly different, but the backslash mapping is the same.
943 { JAVA }
ibm-943_VASCII_VSUB_VPUA
+ x-IBM943 { JAVA }
# japanese. Unicode name is \u30b7\u30d5\u30c8\u7b26\u53f7\u5316\u8868\u73fe
-ibm-33722_P12A-1999 { UTR22* }
+ibm-33722_P12A_P12A-2004_U2 { UTR22* }
ibm-33722 # Leave untagged because this isn't the default
ibm-5050 # Leave untagged because this isn't the default, and yes this alias is correct
- EUC-JP { IANA MIME* WINDOWS JAVA* }
- Extended_UNIX_Code_Packed_Format_for_Japanese { IANA* WINDOWS JAVA }
- csEUCPkdFmtJapanese { IANA WINDOWS JAVA }
- X-EUC-JP { WINDOWS JAVA } # Japan EUC. x-euc-jp is a MIME name
- eucjis { JAVA }
- windows-51932 { WINDOWS* }
- ujis # Linux sometimes uses this name. This is an unfortunate generic and rarely used name. Its use is discouraged.
+ EUC-JP { IANA MIME* WINDOWS }
+ Extended_UNIX_Code_Packed_Format_for_Japanese { IANA* WINDOWS* }
+ csEUCPkdFmtJapanese { IANA WINDOWS }
+ X-EUC-JP { WINDOWS } # Japan EUC. x-euc-jp is a MIME name
ibm-33722_VPUA
IBM-eucJP
+windows-51932-2006 { UTR22* }
+ windows-51932 { WINDOWS* }
+ CP51932 { IANA* }
+ csCP51932
ibm-33722_P120-1999 { UTR22* } # Japan EUC with \ <-> Yen mapping
ibm-33722 { IBM* JAVA }
ibm-5050 { IBM } # Yes this is correct
cp33722 { JAVA* }
33722 { JAVA }
ibm-33722_VASCII_VPUA
-# ibm-954 seems to be almost a superset of ibm-33722
-ibm-954_P101-2000 { UTR22* }
+ x-IBM33722 { JAVA }
+ x-IBM33722A { JAVA }
+ x-IBM33722C { JAVA }
+# ibm-954 seems to be almost a superset of ibm-33722 and ibm-1350
+# ibm-1350 seems to be almost a superset of ibm-33722
+# ibm-954 contains more PUA characters than the others.
+ibm-954_P101-2007 { UTR22* }
ibm-954 { IBM* }
- EUC-JP # This is Solaris EUC-JP.
- # eucJP # A closer Solaris alias
-
-ibm-1373_P100-2002 { UTR22* } # Taiwan Big-5 (w/ euro update)
+ EUC-JP { JAVA* } # Matches more closely with ibm-1350
+ Extended_UNIX_Code_Packed_Format_for_Japanese { JAVA }
+ csEUCPkdFmtJapanese { JAVA }
+ X-EUC-JP { JAVA } # Japan EUC. x-euc-jp is a MIME name
+ eucjis { JAVA }
+ ujis # Linux sometimes uses this name. This is an unfortunate generic and rarely used name. Its use is discouraged.
+ x-IBM954 { JAVA }
+ x-IBM954C { JAVA }
+ # eucJP # This is closest to Solaris EUC-JP.
+
+aix-IBM_udcJP-4.3.6 { UTR22* }
+ x-IBM-udcJP { JAVA* }
+
+java-euc_jp_linux-1.6_P { UTR22* }
+ euc-jp-linux
+ x-EUC_JP_LINUX { JAVA* }
+
+java-sjis_0213-1.6_P { UTR22* }
+ x-SJIS_0213 { JAVA* }
+
+# Here are various interpretations and extentions of Big5
+ibm-1373_P100-2002 { UTR22* } # IBM's interpretation of Windows' Taiwan Big-5 without HKSCS extensions
ibm-1373 { IBM* }
windows-950 # Alternate mapping. Leave untagged. This is the IBM interpretation of a Windows codepage.
windows-950-2000 { UTR22* }
Big5 { IANA* MIME* JAVA* WINDOWS }
csBig5 { IANA WINDOWS }
windows-950 { WINDOWS* }
+ x-windows-950 { JAVA }
x-big5
ibm-950_P110-1999 { UTR22* } # Taiwan Big-5 (w/o euro update)
ibm-950 { IBM* JAVA }
cp950 { JAVA* }
950 { JAVA }
-macos-2566-10.2 { UTR22* } # This uses supplementary characters.
+ x-IBM950 { JAVA }
+ibm-1375_P100-2007 { UTR22* } # Big5-HKSCS-2004 with Unicode 3.1 mappings. This uses supplementary characters.
+ ibm-1375 { IBM* }
Big5-HKSCS { IANA* JAVA* }
big5hk { JAVA }
HKSCS-BIG5 # From http://www.openi18n.org/localenameguide/
- # big5-hkscs:unicode3.0 # This is actually post 3.0 data, which has different mappings
-ibm-1375_P100-2003 { UTR22* } # IBM's interpretation of Windows' Taiwan Big-5 w/ HKSCS extensions
- ibm-1375 { IBM* }
+ibm-5471_P100-2006 { UTR22* } # Big5-HKSCS-2001 with Unicode 3.0 mappings. This uses many PUA characters.
+ ibm-5471 { IBM* }
Big5-HKSCS
MS950_HKSCS { JAVA* }
hkbig5 # from HP-UX 11i, which can't handle supplementary characters.
+ big5-hkscs:unicode3.0
+ x-MS950-HKSCS { JAVA }
# windows-950 # Windows-950 can be w/ or w/o HKSCS extensions. By default it's not.
# windows-950_hkscs
-
-ibm-1386_P100-2002 { UTR22* }
+solaris-zh_TW_big5-2.7 { UTR22* }
+ Big5_Solaris { JAVA* }
+ x-Big5-Solaris { JAVA }
+# GBK
+ibm-1386_P100-2001 { UTR22* }
ibm-1386 { IBM* }
cp1386
windows-936 # Alternate mapping. Leave untagged. This is the IBM interpretation of a Windows codepage.
ibm-1386_VSUB_VPUA
-
windows-936-2000 { UTR22* }
GBK { IANA* WINDOWS JAVA* }
CP936 { IANA JAVA }
cp964 { JAVA* }
964 { JAVA }
ibm-964_VPUA
+ x-IBM964 { JAVA }
# ISO-2022 needs one, and other people may need others.
ibm-949_P110-1999 { UTR22* }
cp949 { JAVA* }
949 { JAVA }
ibm-949_VASCII_VSUB_VPUA
+ x-IBM949 { JAVA }
ibm-949_P11A-1999 { UTR22* }
ibm-949 # Leave untagged because this isn't the default
cp949c { JAVA* }
ibm-949_VSUB_VPUA
+ x-IBM949C { JAVA }
+ IBM-949C { JAVA }
# Korean EUC.
#
# ibm-970 is almost a subset of ibm-1363.
# Java, Solaris and AIX use euc-kr to also mean ksc5601.
# Java has both ibm-970 and EUC-KR as separate converters.
-ibm-970_P110-1995 { UTR22* }
+ibm-970_P110_P110-2006_U2 { UTR22* }
ibm-970 { IBM* JAVA }
EUC-KR { IANA* MIME* WINDOWS JAVA }
KS_C_5601-1987 { JAVA }
cp970 { JAVA* }
970 { JAVA }
ibm-970_VPUA
+ x-IBM970 { JAVA }
# ibm-971 is almost the set of DBCS mappings of ibm-970
-ibm-971_P100-1995 ibm-971 { IBM* } ibm-971_VPUA
+ibm-971_P100-1995 ibm-971 { IBM* } ibm-971_VPUA x-IBM971 { JAVA* }
# Java, Solaris and AIX use euc-kr to also mean ksc5601, and _sometimes_ for Windows too.
# ibm-1363 is almost a superset of ibm-970.
ibm-1363 # Leave untagged because this isn't the default
KS_C_5601-1987 { IANA* }
KS_C_5601-1989 { IANA }
- KSC_5601 { MIME* IANA } # Needed by iso-2022
+ KSC_5601 { IANA }
csKSC56011987 { IANA }
korean { IANA }
iso-ir-149 { IANA }
+ cp1363 { MIME* }
5601
- cp1363
ksc
windows-949 # Alternate mapping. Leave untagged. This is the IBM interpretation of a Windows codepage.
ibm-1363_VSUB_VPUA
+ x-IBM1363C { JAVA* }
# ks_x_1001:1992
# ksc5601-1992
ibm-1363_P110-1997 { UTR22* } # Korean KSC MBCS with \ <-> Won mapping
ibm-1363 { IBM* }
ibm-1363_VASCII_VSUB_VPUA
+ x-IBM1363 { JAVA* }
windows-949-2000 { UTR22* }
windows-949 { JAVA* WINDOWS* }
KS_C_5601-1987 { WINDOWS }
KS_C_5601-1989 { WINDOWS }
- KSC_5601 { WINDOWS } # Needed by iso-2022
+ KSC_5601 { MIME* WINDOWS } # Needed by iso-2022
csKSC56011987 { WINDOWS }
korean { WINDOWS }
iso-ir-149 { WINDOWS }
ms949 { JAVA }
+ x-KSC5601 { JAVA }
+
+windows-1361-2000 { UTR22* }
+ ksc5601_1992
+ ms1361
+ johab
+ x-Johab { JAVA* }
windows-874-2000 { UTR22* } # Thai (w/ euro update)
TIS-620 { WINDOWS }
windows-874 { JAVA* WINDOWS* }
MS874 { JAVA }
+ x-windows-874 { JAVA }
# iso-8859-11 { WINDOWS } # iso-8859-11 is similar to TIS-620. ibm-13162 is a closer match.
ibm-874_P100-1995 { UTR22* } # Thai PC (w/o euro update).
TIS-620 { IANA* JAVA } # This is actually separate from ibm-874, which is similar to this table
tis620.2533 { JAVA } # This is actually separate from ibm-874, which is similar to this table
eucTH # eucTH is an unusual alias from Solaris. eucTH has fewer mappings than TIS620
+ x-IBM874 { JAVA }
ibm-1162_P100-1999 { UTR22* } # Thai (w/ euro update)
ibm-1162 { IBM* }
+windows-864-2000 { UTR22* }
+ ibm-864s
+ cp864s
+ x-IBM864S { JAVA* }
+
# Platform codepages
# If Java supports the IBM prefix, it should also support the ibm- prefix too.
ibm-437_P100-1995 { UTR22* } ibm-437 { IBM* } IBM437 { IANA* WINDOWS JAVA } cp437 { IANA WINDOWS JAVA* } 437 { IANA WINDOWS JAVA } csPC8CodePage437 { IANA JAVA } windows-437 { WINDOWS* } # PC US
-ibm-737_P100-1997 { UTR22* } ibm-737 { IBM* } IBM737 { WINDOWS JAVA } cp737 { JAVA* } windows-737 { WINDOWS* } 737 { JAVA } # PC Greek
+ibm-720_P100-1997 { UTR22* } ibm-720 { IBM* } windows-720 { WINDOWS* } DOS-720 { WINDOWS } x-IBM720 { JAVA* } # PC Arabic
+ibm-737_P100-1997 { UTR22* } ibm-737 { IBM* } IBM737 { WINDOWS JAVA } cp737 { JAVA* } windows-737 { WINDOWS* } 737 { JAVA } x-IBM737 { JAVA } # PC Greek
ibm-775_P100-1996 { UTR22* } ibm-775 { IBM* } IBM775 { IANA* WINDOWS JAVA } cp775 { IANA WINDOWS JAVA* } csPC775Baltic { IANA } windows-775 { WINDOWS* } 775 { JAVA } # PC Baltic
-ibm-850_P100-1995 { UTR22* } ibm-850 { IBM* } IBM850 { IANA* WINDOWS JAVA } cp850 { IANA MIME* WINDOWS JAVA* } 850 { IANA JAVA } csPC850Multilingual { IANA JAVA } windows-850 { WINDOWS* } # PC latin1
+ibm-850_P100-1995 { UTR22* } ibm-850 { IBM* } IBM850 { IANA* MIME* WINDOWS JAVA } cp850 { IANA MIME WINDOWS JAVA* } 850 { IANA JAVA } csPC850Multilingual { IANA JAVA } windows-850 { WINDOWS* } # PC latin1
ibm-851_P100-1995 { UTR22* } ibm-851 { IBM* } IBM851 { IANA* } cp851 { IANA MIME* } 851 { IANA } csPC851 { IANA } # PC DOS Greek (w/o euro)
ibm-852_P100-1995 { UTR22* } ibm-852 { IBM* } IBM852 { IANA* WINDOWS JAVA } cp852 { IANA WINDOWS JAVA* } 852 { IANA WINDOWS JAVA } csPCp852 { IANA JAVA } windows-852 { WINDOWS* } # PC latin2 (w/o euro update)
-ibm-855_P100-1995 { UTR22* } ibm-855 { IBM* } IBM855 { IANA* JAVA } cp855 { IANA JAVA* } 855 { IANA } csIBM855 { IANA } csPCp855 { JAVA } # PC cyrillic (w/o euro update)
-ibm-856_P100-1995 { UTR22* } ibm-856 { IBM* } IBM856 { JAVA } cp856 { MIME* JAVA* } 856 { JAVA } # PC Hebrew (old)
-ibm-857_P100-1995 { UTR22* } ibm-857 { IBM* } IBM857 { IANA* WINDOWS JAVA } cp857 { IANA MIME* JAVA* } 857 { IANA JAVA } csIBM857 { IANA JAVA } windows-857 { WINDOWS* } # PC Latin 5 (w/o euro update)
-ibm-858_P100-1997 { UTR22* } ibm-858 { IBM* } IBM00858 { IANA* JAVA } CCSID00858 { IANA JAVA } CP00858 { IANA JAVA } PC-Multilingual-850+euro { IANA } cp858 { MIME* JAVA* } # PC latin1 with Euro
-ibm-860_P100-1995 { UTR22* } ibm-860 { IBM* } IBM860 { IANA* JAVA } cp860 { IANA MIME* JAVA* } 860 { IANA JAVA } csIBM860 { IANA JAVA } # PC Portugal
-ibm-861_P100-1995 { UTR22* } ibm-861 { IBM* } IBM861 { IANA* WINDOWS JAVA } cp861 { IANA MIME* JAVA* } 861 { IANA JAVA } cp-is { IANA JAVA } csIBM861 { IANA JAVA } windows-861 { WINDOWS* } # PC Iceland
-ibm-862_P100-1995 { UTR22* } ibm-862 { IBM* } IBM862 { IANA* JAVA } cp862 { IANA MIME* JAVA* } 862 { IANA JAVA } csPC862LatinHebrew { IANA JAVA } DOS-862 { WINDOWS } windows-862 { WINDOWS* } # PC Hebrew (w/o euro update)
-ibm-863_P100-1995 { UTR22* } ibm-863 { IBM* } IBM863 { IANA* JAVA } cp863 { IANA MIME* JAVA* } 863 { IANA JAVA } csIBM863 { IANA JAVA } # PC Canadian French
-ibm-864_X110-1999 { UTR22* } ibm-864 { IBM* } IBM864 { IANA* JAVA } cp864 { IANA MIME* JAVA* } csIBM864 { IANA JAVA } # PC Arabic (w/o euro update)
-ibm-865_P100-1995 { UTR22* } ibm-865 { IBM* } IBM865 { IANA* JAVA } cp865 { IANA MIME* JAVA* } 865 { IANA JAVA } csIBM865 { IANA JAVA } # PC Nordic
-ibm-866_P100-1995 { UTR22* } ibm-866 { IBM* } IBM866 { IANA* JAVA } cp866 { IANA MIME* WINDOWS JAVA* } 866 { IANA JAVA } csIBM866 { IANA JAVA } windows-866 { WINDOWS* } # PC Russian (w/o euro update)
-ibm-867_P100-1998 { UTR22* } ibm-867 { IBM* } # PC Hebrew (w/ euro update) Updated version of ibm-862
-ibm-868_P100-1995 { UTR22* } ibm-868 { IBM* } IBM868 { IANA* JAVA } CP868 { IANA MIME* JAVA* } 868 { JAVA } csIBM868 { IANA } cp-ar { IANA } # PC Urdu
-ibm-869_P100-1995 { UTR22* } ibm-869 { IBM* } IBM869 { IANA* WINDOWS JAVA } cp869 { IANA MIME* JAVA* } 869 { IANA JAVA } cp-gr { IANA JAVA } csIBM869 { IANA JAVA } windows-869 { WINDOWS* } # PC Greek (w/o euro update)
+ibm-855_P100-1995 { UTR22* } ibm-855 { IBM* } IBM855 { IANA* JAVA } cp855 { IANA JAVA* } 855 { IANA } csIBM855 { IANA } csPCp855 { JAVA } windows-855 { WINDOWS* } # PC cyrillic (w/o euro update)
+ibm-856_P100-1995 { UTR22* } ibm-856 { IBM* } IBM856 { JAVA } cp856 { JAVA* } 856 { JAVA } x-IBM856 { JAVA } # PC Hebrew implicit order
+ibm-857_P100-1995 { UTR22* } ibm-857 { IBM* } IBM857 { IANA* MIME* WINDOWS JAVA } cp857 { IANA MIME JAVA* } 857 { IANA JAVA } csIBM857 { IANA JAVA } windows-857 { WINDOWS* } # PC Latin 5 (w/o euro update)
+ibm-858_P100-1997 { UTR22* } ibm-858 { IBM* } IBM00858 { IANA* MIME* JAVA } CCSID00858 { IANA JAVA } CP00858 { IANA JAVA } PC-Multilingual-850+euro { IANA } cp858 { MIME JAVA* } windows-858 { WINDOWS* } # PC latin1 with Euro
+ibm-860_P100-1995 { UTR22* } ibm-860 { IBM* } IBM860 { IANA* MIME* JAVA } cp860 { IANA MIME JAVA* } 860 { IANA JAVA } csIBM860 { IANA JAVA } # PC Portugal
+ibm-861_P100-1995 { UTR22* } ibm-861 { IBM* } IBM861 { IANA* MIME* WINDOWS JAVA } cp861 { IANA MIME JAVA* } 861 { IANA JAVA } cp-is { IANA JAVA } csIBM861 { IANA JAVA } windows-861 { WINDOWS* } # PC Iceland
+ibm-862_P100-1995 { UTR22* } ibm-862 { IBM* } IBM862 { IANA* MIME* JAVA } cp862 { IANA MIME JAVA* } 862 { IANA JAVA } csPC862LatinHebrew { IANA JAVA } DOS-862 { WINDOWS } windows-862 { WINDOWS* } # PC Hebrew visual order (w/o euro update)
+ibm-863_P100-1995 { UTR22* } ibm-863 { IBM* } IBM863 { IANA* MIME* JAVA } cp863 { IANA MIME JAVA* } 863 { IANA JAVA } csIBM863 { IANA JAVA } # PC Canadian French
+ibm-864_X110-1999 { UTR22* } ibm-864 { IBM* } IBM864 { IANA* MIME* JAVA } cp864 { IANA MIME JAVA* } csIBM864 { IANA JAVA } # PC Arabic (w/o euro update)
+ibm-865_P100-1995 { UTR22* } ibm-865 { IBM* } IBM865 { IANA* MIME* JAVA } cp865 { IANA MIME JAVA* } 865 { IANA JAVA } csIBM865 { IANA JAVA } # PC Nordic
+ibm-866_P100-1995 { UTR22* } ibm-866 { IBM* } IBM866 { IANA* MIME* JAVA } cp866 { IANA MIME WINDOWS JAVA* } 866 { IANA JAVA } csIBM866 { IANA JAVA } windows-866 { WINDOWS* } # PC Russian (w/o euro update)
+ibm-867_P100-1998 { UTR22* } ibm-867 { IBM* } x-IBM867 { JAVA* } # PC Hebrew (w/ euro update) Updated version of ibm-862
+ibm-868_P100-1995 { UTR22* } ibm-868 { IBM* } IBM868 { IANA* MIME* JAVA } CP868 { IANA MIME JAVA* } 868 { JAVA } csIBM868 { IANA } cp-ar { IANA } # PC Urdu
+ibm-869_P100-1995 { UTR22* } ibm-869 { IBM* } IBM869 { IANA* MIME* WINDOWS JAVA } cp869 { IANA MIME JAVA* } 869 { IANA JAVA } cp-gr { IANA JAVA } csIBM869 { IANA JAVA } windows-869 { WINDOWS* } # PC Greek (w/o euro update)
ibm-878_P100-1996 { UTR22* } ibm-878 { IBM* } KOI8-R { IANA* MIME* WINDOWS JAVA* } koi8 { WINDOWS JAVA } csKOI8R { IANA WINDOWS JAVA } windows-20866 { WINDOWS* } cp878 # Russian internet
ibm-901_P100-1999 { UTR22* } ibm-901 { IBM* } # PC Baltic (w/ euro update), update of ibm-921
ibm-902_P100-1999 { UTR22* } ibm-902 { IBM* } # PC Estonian (w/ euro update), update of ibm-922
-ibm-922_P100-1999 { UTR22* } ibm-922 { IBM* } IBM922 { JAVA } cp922 { MIME* JAVA* } 922 { JAVA } # PC Estonian (w/o euro update)
-ibm-1168_P100-2002 { UTR22* } ibm-1168 { IBM* } KOI8-U { IANA* WINDOWS } windows-21866 { WINDOWS* } koi8-ru { WINDOWS } # Ukrainian KOI8. koi8-ru is an unusual alias, but Microsoft states that it is an alias.
+ibm-922_P100-1999 { UTR22* } ibm-922 { IBM* } IBM922 { JAVA } cp922 { JAVA* } 922 { JAVA } x-IBM922 { JAVA } # PC Estonian (w/o euro update)
+ibm-1168_P100-2002 { UTR22* } ibm-1168 { IBM* } KOI8-U { IANA* WINDOWS } windows-21866 { WINDOWS* } # Ukrainian KOI8. koi8-ru != KOI8-U and Microsoft is wrong for aliasing them as the same.
ibm-4909_P100-1999 { UTR22* } ibm-4909 { IBM* } # ISO Greek (w/ euro update), update of ibm-813
# The cp aliases in this section aren't really windows aliases, but it was used by ICU for Windows.
ibm-5349_P100-1998 { UTR22* } ibm-5349 { IBM* } windows-1253 { IANA* JAVA* WINDOWS* } cp1253 { JAVA } # Windows Greek (w/ euro update)
ibm-5350_P100-1998 { UTR22* } ibm-5350 { IBM* } windows-1254 { IANA* JAVA* WINDOWS* } cp1254 { JAVA } # Windows Turkish (w/ euro update)
ibm-9447_P100-2002 { UTR22* } ibm-9447 { IBM* } windows-1255 { IANA* JAVA* WINDOWS* } cp1255 { JAVA } # Windows Hebrew (w/ euro update)
-ibm-9448_X100-2005 { UTR22* } ibm-9448 { IBM* } windows-1256 { IANA* JAVA* WINDOWS* } cp1256 { WINDOWS JAVA } # Windows Arabic (w/ euro update)
+ibm-9448_X100-2005 { UTR22* } ibm-9448 { IBM* } windows-1256 { IANA* JAVA* WINDOWS* } cp1256 { WINDOWS JAVA } x-windows-1256S { JAVA } # Windows Arabic (w/ euro update)
ibm-9449_P100-2002 { UTR22* } ibm-9449 { IBM* } windows-1257 { IANA* JAVA* WINDOWS* } cp1257 { JAVA } # Windows Baltic (w/ euro update)
ibm-5354_P100-1998 { UTR22* } ibm-5354 { IBM* } windows-1258 { IANA* JAVA* WINDOWS* } cp1258 { JAVA } # Windows Vietnamese (w/ euro update)
ibm-5353_P100-1998 { UTR22* } ibm-5353 { IBM* } windows-1257 # Somewhat old Windows Baltic (w/ euro update)
ibm-1258_P100-1997 { UTR22* } ibm-1258 { IBM* } windows-1258 # Old Windows Vietnamese (w/o euro update)
-macos-0_2-10.2 { UTR22* } macintosh { IANA* MIME* WINDOWS } mac { IANA } csMacintosh { IANA } windows-10000 { WINDOWS* } # Apple latin 1
-macos-6_2-10.4 { UTR22* } x-mac-greek { MIME* WINDOWS } windows-10006 { WINDOWS* } macgr # Apple Greek
-macos-7_3-10.2 { UTR22* } x-mac-cyrillic { MIME* WINDOWS } windows-10007 { WINDOWS* } mac-cyrillic maccy # Apple Cyrillic
-macos-29-10.2 { UTR22* } x-mac-centraleurroman { MIME* } windows-10029 { WINDOWS* } x-mac-ce { WINDOWS } macce # Apple Central Europe
-macos-35-10.2 { UTR22* } x-mac-turkish { MIME* WINDOWS } windows-10081 { WINDOWS* } mactr # Apple Turkish
-
-ibm-1051_P100-1995 { UTR22* } ibm-1051 { IBM* } hp-roman8 { IANA* } roman8 { IANA } r8 { IANA } csHPRoman8 { IANA } # HP Latin1
+macos-0_2-10.2 { UTR22* } macintosh { IANA* MIME* WINDOWS } mac { IANA } csMacintosh { IANA } windows-10000 { WINDOWS* } macroman { JAVA } x-macroman { JAVA* } # Apple latin 1
+macos-6_2-10.4 { UTR22* } x-mac-greek { MIME* WINDOWS } windows-10006 { WINDOWS* } macgr x-MacGreek { JAVA* } # Apple Greek
+macos-7_3-10.2 { UTR22* } x-mac-cyrillic { MIME* WINDOWS } windows-10007 { WINDOWS* } mac-cyrillic maccy x-MacCyrillic { JAVA } x-MacUkraine { JAVA* } # Apple Cyrillic
+macos-21-10.5 { UTR22* } x-mac-thai { MIME* } x-MacThai { JAVA* } MacThai { JAVA }
+macos-29-10.2 { UTR22* } x-mac-centraleurroman { MIME* } windows-10029 { WINDOWS* } x-mac-ce { WINDOWS } macce maccentraleurope x-MacCentralEurope { JAVA* } # Apple Central Europe
+macos-33-10.5 { UTR22* } x-mac-symbol { MIME* } x-MacSymbol { JAVA* } MacSymbol { JAVA }
+macos-34-10.2 { UTR22* } x-mac-dingbat { MIME* } x-MacDingbat { JAVA* } MacDingbat { JAVA }
+macos-35-10.2 { UTR22* } x-mac-turkish { MIME* WINDOWS } windows-10081 { WINDOWS* } mactr x-MacTurkish { JAVA* } # Apple Turkish
+macos-36_2-10.2 { UTR22* } x-mac-croatian { MIME* } x-MacCroatian { JAVA* } MacCroatian { JAVA }
+macos-37_5-10.2 { UTR22* } x-mac-iceland { MIME* } x-MacIceland { JAVA* } MacIceland { JAVA }
+macos-38_2-10.2 { UTR22* } x-mac-romania { MIME* } x-MacRomania { JAVA* } MacRomania { JAVA }
+macos-518-10.2 { UTR22* } x-mac-arabic { MIME* } x-MacArabic { JAVA* } MacArabic { JAVA }
+macos-1285-10.2 { UTR22* } x-mac-hebrew { MIME* } x-MacHebrew { JAVA* } MacHebrew { JAVA }
+
+ibm-1051_P100-1995 { UTR22* } ibm-1051 { IBM* } hp-roman8 { IANA* } roman8 { IANA } r8 { IANA } csHPRoman8 { IANA } x-roman8 { JAVA} # HP Latin1
ibm-1276_P100-1995 { UTR22* } ibm-1276 { IBM* } Adobe-Standard-Encoding { IANA* } csAdobeStandardEncoding { IANA } # Different from ISO-Unicode-IBM-1276 (GCSGID: 1276)
-ibm-1006_P100-1995 { UTR22* } ibm-1006 { IBM* } IBM1006 { JAVA } cp1006 { JAVA* } 1006 { JAVA } # Urdu
-ibm-1098_P100-1995 { UTR22* } ibm-1098 { IBM* } IBM1098 { JAVA } cp1098 { JAVA* } 1098 { JAVA } # PC Farsi
-ibm-1124_P100-1996 { UTR22* } ibm-1124 { IBM* JAVA } cp1124 { JAVA* } 1124 { JAVA } # ISO Cyrillic Ukraine
+ibm-1006_P100-1995 { UTR22* } ibm-1006 { IBM* } IBM1006 { JAVA } cp1006 { JAVA* } 1006 { JAVA } x-IBM1006 { JAVA } # Urdu
+ibm-1098_P100-1995 { UTR22* } ibm-1098 { IBM* } IBM1098 { JAVA } cp1098 { JAVA* } 1098 { JAVA } x-IBM1098 { JAVA } # PC Farsi
+ibm-1124_P100-1996 { UTR22* } ibm-1124 { IBM* JAVA } cp1124 { JAVA* } 1124 { JAVA } x-IBM1124 { JAVA } # ISO Cyrillic Ukraine
ibm-1125_P100-1997 { UTR22* } ibm-1125 { IBM* } cp1125 # Cyrillic Ukraine PC
ibm-1129_P100-1997 { UTR22* } ibm-1129 { IBM* } # ISO Vietnamese
ibm-1131_P100-1997 { UTR22* } ibm-1131 { IBM* } cp1131 # Cyrillic Belarus PC
# Language-specific variants of ISO-2022 continue to be available as listed below.
# ISO_2022 ISO-2022
-ISO_2022,locale=ja,version=0 ISO-2022-JP { IANA* MIME* JAVA* } csISO2022JP { IANA JAVA }
-ISO_2022,locale=ja,version=1 ISO-2022-JP-1 JIS_Encoding { IANA* } csJISEncoding { IANA } ibm-5054 { IBM* } JIS
+ISO_2022,locale=ja,version=0 ISO-2022-JP { IANA* MIME* JAVA* } csISO2022JP { IANA JAVA } x-windows-iso2022jp { JAVA } x-windows-50220 { JAVA }
+ISO_2022,locale=ja,version=1 ISO-2022-JP-1 { MIME* } JIS_Encoding { IANA* } csJISEncoding { IANA } ibm-5054 { IBM* } JIS x-windows-50221 { JAVA* }
ISO_2022,locale=ja,version=2 ISO-2022-JP-2 { IANA* MIME* } csISO2022JP2 { IANA }
ISO_2022,locale=ja,version=3 JIS7
ISO_2022,locale=ja,version=4 JIS8
ISO_2022,locale=ko,version=0 ISO-2022-KR { IANA* MIME* JAVA* } csISO2022KR { IANA JAVA } # This uses ibm-949
ISO_2022,locale=ko,version=1 ibm-25546 { IBM* }
-ISO_2022,locale=zh,version=0 ISO-2022-CN { IANA* JAVA* } csISO2022CN { JAVA }
+ISO_2022,locale=zh,version=0 ISO-2022-CN { IANA* JAVA* } csISO2022CN { JAVA } x-ISO-2022-CN-GB { JAVA }
ISO_2022,locale=zh,version=1 ISO-2022-CN-EXT { IANA* }
+ISO_2022,locale=zh,version=2 ISO-2022-CN-CNS x-ISO-2022-CN-CNS { JAVA* }
HZ HZ-GB-2312 { IANA* }
+x11-compound-text COMPOUND_TEXT x-compound-text { JAVA* }
-# Part of iso-2022
-ibm-897_P100-1995 { UTR22* } ibm-897 { IBM* } JIS_X0201 { IANA* } X0201 { IANA } csHalfWidthKatakana { IANA }
-
-
-ISCII,version=0 x-iscii-de { WINDOWS } windows-57002 { WINDOWS* } iscii-dev
+ISCII,version=0 x-ISCII91 { JAVA* } x-iscii-de { WINDOWS } windows-57002 { WINDOWS* } iscii-dev ibm-4902 { IBM* } # ibm-806 contains non-standard box drawing symbols.
ISCII,version=1 x-iscii-be { WINDOWS } windows-57003 { WINDOWS* } iscii-bng windows-57006 { WINDOWS } x-iscii-as { WINDOWS } # be is different from as on Windows.
ISCII,version=2 x-iscii-pa { WINDOWS } windows-57011 { WINDOWS* } iscii-gur
ISCII,version=3 x-iscii-gu { WINDOWS } windows-57010 { WINDOWS* } iscii-guj
LMBCS-1 lmbcs ibm-65025 { IBM* }
# These Lotus specific converters still work, but they aren't advertised in this alias table.
-# These are almost never used outside of Lotus software, and they take a lot of time when creating the available converter list.
+# These are almost never used outside of Lotus software,
+# and they take a lot of time when creating the available converter list.
+# Also Lotus doesn't really use them anyway. It was a mistake to create these LMBCS variant converters in ICU.
#LMBCS-2
#LMBCS-3
#LMBCS-4
ibm-838_P100-1995 { UTR22* } ibm-838 { IBM* } IBM838 { JAVA } IBM-Thai { IANA* JAVA } csIBMThai { IANA } cp838 { JAVA* } 838 { JAVA } ibm-9030 { IBM } # EBCDIC Thai. Yes ibm-9030 is an alias.
ibm-870_P100-1995 { UTR22* } ibm-870 { IBM* } IBM870 { IANA* JAVA } CP870 { IANA JAVA* } ebcdic-cp-roece { IANA } ebcdic-cp-yu { IANA } csIBM870 { IANA } # EBCDIC Latin 2
ibm-871_P100-1995 { UTR22* } ibm-871 { IBM* } IBM871 { IANA* JAVA } ebcdic-cp-is { IANA JAVA } csIBM871 { IANA JAVA } CP871 { IANA JAVA* } ebcdic-is { JAVA } 871 { JAVA } # EBCDIC Iceland
-ibm-875_P100-1995 { UTR22* } ibm-875 { IBM* } IBM875 { JAVA } cp875 { JAVA* } 875 { JAVA } # EBCDIC Greek
+ibm-875_P100-1995 { UTR22* } ibm-875 { IBM* } IBM875 { JAVA } cp875 { JAVA* } 875 { JAVA } x-IBM875 { JAVA } # EBCDIC Greek
ibm-918_P100-1995 { UTR22* } ibm-918 { IBM* } IBM918 { IANA* JAVA } CP918 { IANA JAVA* } ebcdic-cp-ar2 { IANA } csIBM918 { IANA } # EBCDIC Urdu
ibm-930_P120-1999 { UTR22* } # EBCDIC_STATEFUL Katakana-Kanji Host Mixed.
ibm-930 { IBM* }
IBM930 { JAVA }
cp930 { JAVA* }
930 { JAVA }
-ibm-933_P110-1995 { UTR22* } ibm-933 { IBM* JAVA } cp933 { JAVA* } 933 { JAVA } # Korea EBCDIC MIXED
-ibm-935_P110-1999 { UTR22* } ibm-935 { IBM* JAVA } cp935 { JAVA* } 935 { JAVA } # China EBCDIC MIXED. Need to use Unicode, ibm-1388 or gb18030 instead because it is required by the government of China.
-ibm-937_P110-1999 { UTR22* } ibm-937 { IBM* JAVA } cp937 { JAVA* } 937 { JAVA } # Taiwan EBCDIC MIXED
+ x-IBM930 { JAVA }
+ x-IBM930A { JAVA }
+ibm-933_P110-1995 { UTR22* } ibm-933 { IBM* JAVA } cp933 { JAVA* } 933 { JAVA } x-IBM933 { JAVA } # Korea EBCDIC MIXED
+ibm-935_P110-1999 { UTR22* } ibm-935 { IBM* JAVA } cp935 { JAVA* } 935 { JAVA } x-IBM935 { JAVA } # China EBCDIC MIXED. Need to use Unicode, ibm-1388 or gb18030 instead because it is required by the government of China.
+ibm-937_P110-1999 { UTR22* } ibm-937 { IBM* JAVA } cp937 { JAVA* } 937 { JAVA } x-IBM937 { JAVA } # Taiwan EBCDIC MIXED
ibm-939_P120-1999 { UTR22* } # EBCDIC_STATEFUL Latin-Kanji Host Mixed.
ibm-939 { IBM* }
ibm-931 { IBM } # Yes this is correct
IBM939 { JAVA }
cp939 { JAVA* }
939 { JAVA }
-ibm-1025_P100-1995 { UTR22* } ibm-1025 { IBM* JAVA } cp1025 { JAVA* } 1025 { JAVA } # EBCDIC Cyrillic
+ x-IBM939 { JAVA }
+ x-IBM939A { JAVA }
+ibm-1025_P100-1995 { UTR22* } ibm-1025 { IBM* JAVA } cp1025 { JAVA* } 1025 { JAVA } x-IBM1025 { JAVA } # EBCDIC Cyrillic
ibm-1026_P100-1995 { UTR22* } ibm-1026 { IBM* } IBM1026 { IANA* JAVA } CP1026 { IANA JAVA* } csIBM1026 { IANA } 1026 { JAVA } # EBCDIC Turkey
ibm-1047_P100-1995 { UTR22* } ibm-1047 { IBM* } IBM1047 { IANA* JAVA } cp1047 { JAVA* } 1047 { JAVA } # EBCDIC Open systems Latin1
-ibm-1097_P100-1995 { UTR22* } ibm-1097 { IBM* JAVA } cp1097 { JAVA* } 1097 { JAVA } # EBCDIC Farsi
-ibm-1112_P100-1995 { UTR22* } ibm-1112 { IBM* JAVA } cp1112 { JAVA* } 1112 { JAVA } # EBCDIC Baltic
-ibm-1122_P100-1999 { UTR22* } ibm-1122 { IBM* JAVA } cp1122 { JAVA* } 1122 { JAVA } # EBCDIC Estonia
-ibm-1123_P100-1995 { UTR22* } ibm-1123 { IBM* JAVA } cp1123 { JAVA* } 1123 { JAVA } # EBCDIC Cyrillic Ukraine
+ibm-1097_P100-1995 { UTR22* } ibm-1097 { IBM* JAVA } cp1097 { JAVA* } 1097 { JAVA } x-IBM1097 { JAVA } # EBCDIC Farsi
+ibm-1112_P100-1995 { UTR22* } ibm-1112 { IBM* JAVA } cp1112 { JAVA* } 1112 { JAVA } x-IBM1112 { JAVA } # EBCDIC Baltic
+ibm-1114_P100-2001 { UTR22* } ibm-1114 { IBM* } x-IBM1114 { JAVA* }
+ibm-1115_P100-1995 { UTR22* } ibm-1115 { IBM* } x-IBM1115 { JAVA* }
+ibm-1122_P100-1999 { UTR22* } ibm-1122 { IBM* JAVA } cp1122 { JAVA* } 1122 { JAVA } x-IBM1122 { JAVA } # EBCDIC Estonia
+ibm-1123_P100-1995 { UTR22* } ibm-1123 { IBM* JAVA } cp1123 { JAVA* } 1123 { JAVA } x-IBM1123 { JAVA } # EBCDIC Cyrillic Ukraine
ibm-1130_P100-1997 { UTR22* } ibm-1130 { IBM* } # EBCDIC Vietnamese
ibm-1132_P100-1998 { UTR22* } ibm-1132 { IBM* } # EBCDIC Lao
ibm-1137_P100-1999 { UTR22* } ibm-1137 { IBM* } # Devanagari EBCDIC (based on Unicode character set)
ibm-1147_P100-1997 { UTR22* } ibm-1147 { IBM* } IBM01147 { IANA* JAVA } CCSID01147 { IANA JAVA } CP01147 { IANA JAVA } cp1147 { JAVA* } ebcdic-fr-297+euro { IANA } # EBCDIC France
ibm-1148_P100-1997 { UTR22* } ibm-1148 { IBM* } IBM01148 { IANA* JAVA } CCSID01148 { IANA JAVA } CP01148 { IANA JAVA } cp1148 { JAVA* } ebcdic-international-500+euro { IANA } # EBCDIC International Latin1
ibm-1149_P100-1997 { UTR22* } ibm-1149 { IBM* } IBM01149 { IANA* JAVA } CCSID01149 { IANA JAVA } CP01149 { IANA JAVA } cp1149 { JAVA* } ebcdic-is-871+euro { IANA } # EBCDIC Iceland
-ibm-1153_P100-1999 { UTR22* } ibm-1153 { IBM* } # EBCDIC latin 2
+ibm-1153_P100-1999 { UTR22* } ibm-1153 { IBM* } IBM1153 { JAVA } x-IBM1153 { JAVA* } # EBCDIC latin 2
ibm-1154_P100-1999 { UTR22* } ibm-1154 { IBM* } # EBCDIC Cyrillic Multilingual
ibm-1155_P100-1999 { UTR22* } ibm-1155 { IBM* } # EBCDIC Turkey
ibm-1156_P100-1999 { UTR22* } ibm-1156 { IBM* } # EBCDIC Baltic Multilingual
ibm-1158_P100-1999 { UTR22* } ibm-1158 { IBM* } # EBCDIC Cyrillic Ukraine
ibm-1160_P100-1999 { UTR22* } ibm-1160 { IBM* } # EBCDIC Thailand
ibm-1164_P100-1999 { UTR22* } ibm-1164 { IBM* } # EBCDIC Viet Nam
-ibm-1364_P110-1997 { UTR22* } ibm-1364 { IBM* } # Korean Host Mixed
-ibm-1371_P100-1999 { UTR22* } ibm-1371 { IBM* } # Taiwan EBCDIC MIXED
-ibm-1388_P103-2001 { UTR22* } ibm-1388 { IBM* } ibm-9580 { IBM } # S-Ch DBCS-Host Data GBK EBCDIC_STATEFUL. Yes ibm-9580 is an alias.
-ibm-1390_P110-2003 { UTR22* } ibm-1390 { IBM* } # Japan EBCDIC MIXED (JIS X 0213)
-ibm-1399_P110-2003 { UTR22* } ibm-1399 { IBM* } # Host MBCS (Latin-Kanji) (JIS X 0213)
+ibm-1364_P110-2007 { UTR22* } ibm-1364 { IBM* } x-IBM1364 { JAVA* } # Korean Host Mixed
+ibm-1370_P100-1999 { UTR22* } ibm-1370 { IBM* } x-IBM1370 { JAVA* }
+ibm-1371_P100-1999 { UTR22* } ibm-1371 { IBM* } x-IBM1371 { JAVA* } # Taiwan EBCDIC MIXED (Euro update of ibm-937)
+ibm-1388_P103-2001 { UTR22* } ibm-1388 { IBM* } ibm-9580 { IBM } x-IBM1388 { JAVA* } # S-Ch DBCS-Host Data GBK EBCDIC_STATEFUL. Yes ibm-9580 is an alias.
+ibm-1390_P110-2003 { UTR22* } ibm-1390 { IBM* } x-IBM1390 { JAVA* } # Japan EBCDIC MIXED (JIS X 0213)
+ibm-1399_P110-2003 { UTR22* } ibm-1399 { IBM* } x-IBM1399 { JAVA* } # Host MBCS (Latin-Kanji) (JIS X 0213)
ibm-5123_P100-1999 { UTR22* } ibm-5123 { IBM* } # Host Roman Jis. Euro update of ibm-1027. SBCS portion of ibm-1390.
ibm-8482_P100-1999 { UTR22* } ibm-8482 { IBM* } # host SBCS (Katakana). Euro update of ibm-290. SBCS portion of ibm-1399.
-ibm-16684_P110-2003 { UTR22* } ibm-16684 { IBM* } # DBCS Jis + Roman Jis Host. This is the DBCS portion of ibm-1390 and ibm-1399 (JIS X 0213)
+# Yes ibm-20780 is the same as ibm-16684
+ibm-16684_P110-2003 { UTR22* } ibm-16684 { IBM* } ibm-20780 { IBM } # DBCS Jis + Roman Jis Host. This is the DBCS portion of ibm-1390 and ibm-1399 (JIS X 0213).
ibm-4899_P100-1998 { UTR22* } ibm-4899 { IBM* } # Old EBCDIC Hebrew. Update of ibm-803
+ibm-4971_P100-1999 { UTR22* } ibm-4971 { IBM* } # EBCDIC Greek. Update of ibm-875 and superceded by ibm-9067
ibm-9067_X100-2005 { UTR22* } ibm-9067 { IBM* } # EBCDIC Greek. Update of ibm-875 and ibm-4971
ibm-12712_P100-1998 { UTR22* } ibm-12712 { IBM* } ebcdic-he # EBCDIC Hebrew (new sheqel, control charaters update). Update of ibm-424
ibm-16804_X110-1999 { UTR22* } ibm-16804 { IBM* } ebcdic-ar # EBCDIC Arabic. Update of ibm-420
+java-Cp1399A-1.6_P { UTR22* } x-IBM1399A { JAVA* }
+java-Cp420s-1.6_P { UTR22* } x-IBM420S { JAVA* }
+java-Cp1390A-1.6_P { UTR22* } x-IBM1390A { JAVA* }
# EBCDIC codepages for S/390, with LF and NL codes swapped
# Starting with ICU 2.4, the swapping is done by modifying the
# they are already covered by the normal option parsing together with the
# regular, option-less alias elsewhere in this file.
-ibm-37_P100-1995,swaplfnl ibm-37-s390 ibm037-s390
-ibm-1047_P100-1995,swaplfnl ibm-1047-s390
+ibm-37_P100-1995,swaplfnl ibm-37-s390 # ibm037-s390 also matches ibm-37-s390
+ibm-924_P100-1998,swaplfnl ibm-924-s390 IBM924_LF { JAVA* }
+ibm-1047_P100-1995,swaplfnl ibm-1047-s390 IBM1047_LF { JAVA* }
ibm-1140_P100-1997,swaplfnl ibm-1140-s390
+ibm-1141_P100-1997,swaplfnl ibm-1141-s390 IBM1141_LF { JAVA* }
ibm-1142_P100-1997,swaplfnl ibm-1142-s390
ibm-1143_P100-1997,swaplfnl ibm-1143-s390
ibm-1144_P100-1997,swaplfnl ibm-1144-s390
ebcdic-xml-us
-# TODO Consider removing this table
-ibm-4971_P100-1999 { UTR22* } ibm-4971 { IBM* } # EBCDIC Greek. Update of ibm-875 and superceded by ibm-9067
-
-
-# These were removed due to age, and they are rarely used.
-
-# ibm-274 IBM274 { IANA* } cp274 csIBM274 ebcdic-be
-# ibm-870 IBM870 { IANA* } ebcdic-cp-roece ebcdic-cp-yu csIBM870 cp870 870
-
-#ibm-942_P120-1999 { UTR22* }
-# #ibm-942 { IBM* }
-# ibm-942_VASCII_VSUB_VPUA
-# #ibm-932 { IBM }
-# ibm-932_VASCII_VSUB_VPUA # Old s_jis
-#ibm-859 { IBM* } cp859 { MIME* } # PC Latin 9 (w/ euro update)
-#ibm-5104_X110-1999 { UTR22* } ibm-5104 { IBM* } cp1008 # 8-bit Arabic (w/ euro update)
-#ibm-9238 { IBM* } cp1046 # PC Arabic Extended (w/ euro update)
-#ibm-17248_X110-1999 { UTR22* } ibm-17248 { IBM* } # PC Arabic (w/ euro update) Updated version of ibm-864
-
-#ibm-941 jis-208 jisx-208 # Pure DBCS jisx-208 # ibm-941 is not JISX 208 code page
-#ibm-955 jis-208 jisx-208 # Pure DBCS jisx-208
-
-#ibm-1159_P100-1999 { UTR22* } ibm-1159 { IBM* } # SBCS T-Ch Host. Euro update of ibm-28709. This is used in combination with another CCSID mapping.
-#ibm-9027_P100-1999 { UTR22* } ibm-9027 { IBM* } # DBCS T-Ch Host. Euro update of ibm-835. DBCS portion of ibm-1371.
-
-#ibm-1381_P110-1999 { UTR22* } ibm-1381 { IBM* JAVA } cp1381 { JAVA* } 1381 { JAVA } # S-Ch PC Data mixed (IBM GB)
-
+# These are not installed by default. They are rarely used.
+# Many of them can be added through the online ICU Data Library Customization tool
+
+gsm-03.38-2000 { UTR22* } GSM0338 # GSM0338 alias is from Perl
+ibm-1004_P100-1995 { UTR22* } ibm-1004 { IBM* }
+ibm-1008_P100-1995 { UTR22* } ibm-1008 { IBM* } # cp1008, 8-bit Arabic (w/o euro update)
+ibm-1009_P100-1995 { UTR22* } ibm-1009 { IBM* }
+ibm-1010_P100-1995 { UTR22* } ibm-1010 { IBM* } NF_Z_62-010 { IANA* } iso-ir-69 { IANA } ISO646-FR { IANA } fr { IANA } csISO69French { IANA }
+ibm-1011_P100-1995 { UTR22* } ibm-1011 { IBM* } DIN_66003 { IANA* } iso-ir-21 { IANA } de { IANA } ISO646-DE { IANA } csISO21German { IANA }
+ibm-1012_P100-1995 { UTR22* } ibm-1012 { IBM* } IT { IANA* } iso-ir-15 { IANA } ISO646-IT { IANA } csISO15Italian { IANA }
+ibm-1013_P100-1995 { UTR22* } ibm-1013 { IBM* } BS_4730 { IANA* } iso-ir-4 { IANA } ISO646-GB { IANA } gb { IANA } uk { IANA } csISO4UnitedKingdom { IANA }
+ibm-1014_P100-1995 { UTR22* } ibm-1014 { IBM* } ES2 { IANA* } iso-ir-85 { IANA } ISO646-ES2 { IANA } csISO85Spanish2 { IANA }
+ibm-1015_P100-1995 { UTR22* } ibm-1015 { IBM* } PT2 { IANA* } iso-ir-84 { IANA } ISO646-PT2 { IANA } csISO84Portuguese2 { IANA }
+ibm-1016_P100-1995 { UTR22* } ibm-1016 { IBM* } NS_4551-1 { IANA* } iso-ir-60 { IANA } ISO646-NO { IANA } no { IANA } csISO60DanishNorwegian { IANA } csISO60Norwegian1 { IANA }
+ibm-1017_P100-1995 { UTR22* } ibm-1017 { IBM* }
+ibm-1018_P100-1995 { UTR22* } ibm-1018 { IBM* } SEN_850200_B { IANA* } iso-ir-10 { IANA } FI { IANA } ISO646-FI { IANA } ISO646-SE { IANA } se { IANA } csISO10Swedish { IANA }
+ibm-1019_P100-1995 { UTR22* } ibm-1019 { IBM* }
+ibm-1020_P100-2003 { UTR22* } ibm-1020 { IBM* } CSA_Z243.4-1985-1 { IANA* } iso-ir-121 { IANA } ISO646-CA { IANA } csa7-1 { IANA } ca { IANA } csISO121Canadian1 { IANA }
+ibm-1021_P100-2003 { UTR22* } ibm-1021 { IBM* }
+ibm-1023_P100-2003 { UTR22* } ibm-1023 { IBM* } ES { IANA* } iso-ir-17 { IANA } ISO646-ES { IANA } csISO17Spanish { IANA }
+ibm-1027_P100-1995 { UTR22* } ibm-1027 { IBM* } x-IBM1027 { JAVA* }
+ibm-1041_P100-1995 { UTR22* } ibm-1041 { IBM* } x-IBM1041 { JAVA* }
+ibm-1043_P100-1995 { UTR22* } ibm-1043 { IBM* } x-IBM1043 { JAVA* }
+ibm-1046_X110-1999 { UTR22* } ibm-1046 { IBM* } x-IBM1046 { JAVA* } x-IBM1046S { JAVA } # Arabic
+ibm-1088_P100-1995 { UTR22* } ibm-1088 { IBM* } x-IBM1088 { JAVA* }
+ibm-1100_P100-2003 { UTR22* } ibm-1100 { IBM* } DEC-MCS { IANA* } dec { IANA } csDECMCS { IANA }
+ibm-1101_P100-2003 { UTR22* } ibm-1101 { IBM* }
+ibm-1102_P100-2003 { UTR22* } ibm-1102 { IBM* }
+ibm-1103_P100-2003 { UTR22* } ibm-1103 { IBM* }
+ibm-1104_P100-2003 { UTR22* } ibm-1104 { IBM* } NF_Z_62-010_1973 iso-ir-25 { IANA* } ISO646-FR1 { IANA } csISO25French { IANA } # NF_Z_62-010_(1973) is the real IANA alias, but () aren't invariant characters.
+ibm-1105_P100-2003 { UTR22* } ibm-1105 { IBM* }
+ibm-1106_P100-2003 { UTR22* } ibm-1106 { IBM* }
+ibm-1107_P100-2003 { UTR22* } ibm-1107 { IBM* } DS_2089 { IANA* } ISO646-DK { IANA } dk { IANA } csISO646Danish { IANA }
+ibm-1127_P100-2004 { UTR22* } ibm-1127 { IBM* }
+ibm-1161_P100-1999 { UTR22* } ibm-1161 { IBM* } # Thai (Euro update of ibm-1129)
+ibm-1163_P100-1999 { UTR22* } ibm-1163 { IBM* } # Vietnamese
+ibm-1165_P101-2000 { UTR22* } ibm-1165 { IBM* } # Vietnamese (EBCDIC)
+ibm-1166_P100-2002 { UTR22* } ibm-1166 { IBM* } # Cyrillic for Kazakhstan
+ibm-1167_P100-2002 { UTR22* } ibm-1167 { IBM* } KOI8-RU x-KOI8_RU { JAVA* }
+ibm-1174_X100-2007 { UTR22* } ibm-1174 { IBM* } KZ-1048 { IANA* } STRK1048-2002 { IANA } RK1048 { IANA } csKZ1048 { IANA }
+ibm-1277_P100-1995 { UTR22* } ibm-1277 { IBM* } # Adobe (Postscript) Latin-1
+ibm-13125_P100-1997 { UTR22* } ibm-13125 { IBM* } # S-Ch (DBCS subset of ibm-4933, ibm-1388)
+ibm-13140_P101-2000 { UTR22* } ibm-13140 { IBM* }
+ibm-13218_P100-1996 { UTR22* } ibm-13218 { IBM* } # Japanese (EBCDIC update of ibm-930)
+ibm-1350_P110-1997 { UTR22* } ibm-1350 { IBM* } x-eucJP-Open { JAVA* } eucJP-Open { JAVA } # Japanese (EUC-JP variant)
+ibm-1351_P110-1997 { UTR22* } ibm-1351 { IBM* } x-IBM1351 { JAVA* } # Japanese (DBCS subset of ibm-5039)
+ibm-1362_P110-1999 { UTR22* } ibm-1362 { IBM* } x-IBM1362 { JAVA* } # Korean (DBCS subset of ibm-1363)
+ibm-13676_P102-2001 { UTR22* } ibm-13676 { IBM* } # Simplified Chinese (EBCDIC)
+ibm-1380_P100-1995 { UTR22* } ibm-1380 { IBM* } x-IBM1380 { JAVA* } # Simplified Chinese (DBCS subset of ibm-1381)
+ibm-1381_P110-1999 { UTR22* } ibm-1381 { IBM* JAVA } cp1381 { JAVA* } 1381 { JAVA } x-IBM1381 { JAVA } # Simplified Chinese PC Data mixed (IBM GB)
+ibm-1382_P100-1995 { UTR22* } ibm-1382 { IBM* } x-IBM1382 { JAVA* } # Simplified Chinese (DBCS subset of ibm-1383)
+ibm-17221_P100-2001 { UTR22* } ibm-17221 { IBM* } # Simplified Chinese (EBCDIC)
+ibm-17248_X110-1999 { UTR22* } ibm-17248 { IBM* } # PC Arabic (w/ euro update) Updated version of ibm-864
+ibm-21344_P101-2000 { UTR22* } ibm-21344 { IBM* } # PC Arabic. Updated version of ibm-864
+ibm-21427_P100-1999 { UTR22* } ibm-21427 { IBM* } # Traditional Chinese (DBCS subset of ibm-1370)
+ibm-256_P100-1995 { UTR22* } ibm-256 { IBM* } # Latin 1 EBCDIC
+ibm-259_P100-1995 { UTR22* } ibm-259 { IBM* } IBM-Symbols { IANA* } csIBMSymbols { IANA }
+ibm-274_P100-2000 { UTR22* } ibm-274 { IBM* } IBM274 { IANA* } EBCDIC-BE { IANA } CP274 { IANA } csIBM274 { IANA }
+ibm-275_P100-1995 { UTR22* } ibm-275 { IBM* } IBM275 { IANA* } EBCDIC-BR { IANA } cp275 { IANA } csIBM275 { IANA }
+ibm-286_P100-2003 { UTR22* } ibm-286 { IBM* } EBCDIC-AT-DE-A { IANA* } csEBCDICATDEA { IANA }
+ibm-293_P100-1995 { UTR22* } ibm-293 { IBM* } # APL EBCDIC (APL: A Programming Language)
+ibm-300_P120-2006 { UTR22* } ibm-300 { IBM* } x-IBM300 { JAVA* } # Japanese (DBCS subset of ibm-930 and ibm-939)
+ibm-301_P110-1997 { UTR22* } ibm-301 { IBM* } x-IBM301 { JAVA* } # Japanese (DBCS subset of ibm-943)
+ibm-33058_P100-2000 { UTR22* } ibm-33058 { IBM* } # SBCS (Katakana)
+ibm-425_P101-2000 { UTR22* } ibm-425 { IBM* } # Arabic (EBCDIC)
+ibm-4930_P110-1999 { UTR22* } ibm-4930 { IBM* } # Korean (DBCS subset of ibm-1364)
+ibm-4933_P100-2002 { UTR22* } ibm-4933 { IBM* } # S-Ch (DBCS subset of ibm-1388)
+ibm-4948_P100-1995 { UTR22* } ibm-4948 { IBM* }
+ibm-4951_P100-1995 { UTR22* } ibm-4951 { IBM* }
+ibm-4952_P100-1995 { UTR22* } ibm-4952 { IBM* }
+ibm-4960_P100-1995 { UTR22* } ibm-4960 { IBM* }
+ibm-5039_P11A-1998 { UTR22* } ibm-5039 { IBM* } # Japanese (HP Shift-JIS variant)
+ibm-5048_P100-1995 { UTR22* } ibm-5048 { IBM* } # Japanese (DBCS subset of ibm-1350, JIS X208-1990)
+ibm-5049_P100-1995 { UTR22* } ibm-5049 { IBM* } # Japanese (DBCS subset of ibm-1350, JIS X212)
+ibm-5067_P100-1995 { UTR22* } ibm-5067 { IBM* } # Korean (DBCS subset of ibm-21450)
+ibm-5104_X110-1999 { UTR22* } ibm-5104 { IBM* } # cp1008, 8-bit Arabic (w/ euro update)
+ibm-806_P100-1998 { UTR22* } ibm-806 { IBM* } # Hindi (ISCII variant)
+ibm-808_P100-1999 { UTR22* } ibm-808 { IBM* } x-IBM808 { JAVA* } # Cyrillic
+ibm-833_P100-1995 { UTR22* } ibm-833 { IBM* } x-IBM833 { JAVA* }
+ibm-834_P100-1995 { UTR22* } ibm-834 { IBM* } x-IBM834 { JAVA* } # Korean (DBCS subset of ibm-933)
+ibm-835_P100-1995 { UTR22* } ibm-835 { IBM* } x-IBM835 { JAVA* } # Traditional Chinese (DBCS subset of ibm-5033)
+ibm-836_P100-1995 { UTR22* } ibm-836 { IBM* } x-IBM836 { JAVA* }
+ibm-837_P100-1995 { UTR22* } ibm-837 { IBM* } x-IBM837 { JAVA* } # Simplified Chinese (DBCS subset of ibm-5031)
+ibm-848_P100-1999 { UTR22* } ibm-848 { IBM* } # Cyrillic (euro update of ibm-1125)
+ibm-849_P100-1999 { UTR22* } ibm-849 { IBM* } # Cyrillic Belarus (euro update of ibm-1131)
+ibm-859_P100-1999 { UTR22* } ibm-859 { IBM* } x-IBM859 { JAVA* } # PC Latin 9 (w/ euro update)
+ibm-8612_P100-1995 { UTR22* } ibm-8612 { IBM* } # Arabic (EBCDIC update of ibm-420)
+ibm-872_P100-1999 { UTR22* } ibm-872 { IBM* } # Cyrillic (Euro update of ibm-855)
+ibm-880_P100-1995 { UTR22* } ibm-880 { IBM* } IBM880 { IANA* } cp880 { IANA } EBCDIC-Cyrillic { IANA } csIBM880 { IANA } windows-20880 { WINDOWS* }
+ibm-896_P100-1995 { UTR22* } ibm-896 { IBM* } # SBCS Katakana
+ibm-897_P100-1995 { UTR22* } ibm-897 { IBM* } JIS_X0201 { IANA* } X0201 { IANA } csHalfWidthKatakana { IANA } x-IBM897 { JAVA* }
+ibm-9027_P100-1999 { UTR22* } ibm-9027 { IBM* } # DBCS T-Ch Host. Euro update of ibm-835. DBCS portion of ibm-1371.
+ibm-9048_P100-1998 { UTR22* } ibm-9048 { IBM* } # Hebrew (Euro and Sequel update of ibm-856)
+ibm-905_P100-1995 { UTR22* } ibm-905 { IBM* } IBM905 { IANA* } CP905 { IANA } ebcdic-cp-tr { IANA } csIBM905 { IANA } windows-20905 { WINDOWS* }
+ibm-9056_P100-1995 { UTR22* } ibm-9056 { IBM* } # Arabic
+ibm-9061_P100-1999 { UTR22* } ibm-9061 { IBM* } # Greek (w/ euro update)
+ibm-9145_P110-1997 { UTR22* } ibm-9145 { IBM* } # Japanese (DBCS subset of ibm-5050)
+ibm-9238_X110-1999 { UTR22* } ibm-9238 { IBM* } # cp1046, PC Arabic Extended (w/ euro update)
+ibm-924_P100-1998 { UTR22* } ibm-924 { IBM* } IBM00924 { IANA* } CCSID00924 { IANA } CP00924 { IANA } ebcdic-Latin9--euro { IANA }
+ibm-926_P100-2000 { UTR22* } ibm-926 { IBM* } # Korean (DBCS subset of ibm-944)
+ibm-927_P100-1995 { UTR22* } ibm-927 { IBM* } x-IBM927 { JAVA* } # Traditional Chinese (DBCS subset of ibm-948)
+ibm-928_P100-1995 { UTR22* } ibm-928 { IBM* } # Simplified Chinese (DBCS subset of ibm-936)
+ibm-941_P13A-2001 { UTR22* } ibm-941 { IBM* } # DBCS portion of ibm-943
+ibm-944_P100-1995 { UTR22* } ibm-944 { IBM* } # Korean
+ibm-946_P100-1995 { UTR22* } ibm-946 { IBM* } # Simplified Chinese
+ibm-947_P100-1995 { UTR22* } ibm-947 { IBM* } x-IBM947 { JAVA* } # Traditional Chinese (DBCS subset of ibm-950)
+ibm-948_P110-1999 { UTR22* } ibm-948 { IBM* } x-IBM948 { JAVA* } # Traditional Chinese
+ibm-951_P100-1995 { UTR22* } ibm-951 { IBM* } x-IBM951 { JAVA* } # Korean (DBCS subset of ibm-949)
+ibm-952_P110-1997 { UTR22* } ibm-952 { IBM* } x-JIS0208 # Pure DBCS, Japanese EUC, G1 - JIS X208-1990
+ibm-953_P100-2000 { UTR22* } ibm-953 { IBM* } JIS_X0212-1990 { IANA* } # Pure DBCS, Japanese EUC, G3 - JIS X 0212-1990
+ibm-955_P110-1997 { UTR22* } ibm-955 { IBM* } # Pure DBCS, Japanese EUC, G0 - JIS X208-1978
+ibm-9577_P100-2001 { UTR22* } ibm-9577 { IBM* } ibm-1385 { IBM } x-IBM1385 { JAVA* } # ibm-9577 and ibm-1385 are identical DBCS tables.
+iso-8859_16-2001 { UTR22* } ISO-8859-16 { IANA* } iso-ir-226 { IANA } ISO_8859-16:2001 { IANA } latin10 { IANA } l10 { IANA }
+
+# To be considered for listing at a later date for the data library customization tool
+#ibm-1159_P100-1999 { UTR22* } ibm-1159 { IBM* } # SBCS T-Ch Host. Euro update of ibm-28709. This is used in combination with another CCSID mapping.
+#ibm-960_P100-2000 { UTR22* } ibm-960 { IBM* } # Pure DBCS, CNS11643 plane 1
+#ibm-963_P100-1995 { UTR22* } ibm-963 { IBM* } # Pure DBCS, CNS11643 plane 2 Traditional Chinese (DBCS subset of ibm-965)
projects / apple / icu.git / blobdiff